Radio frequency sensing for cognitive load and neurodegeneration monitoring with AI-driven classification

Abstract

Cognitive load is a significant early indicator of neurodegeneration. Capturing early signs of cognitive load could delay the onset of acute dementia and other neurodegenerative conditions.

Neurodegenerative diseases, such as dementia and Alzheimer’s disease, significantly impact the healthcare sector by increasing long-term care needs, raising healthcare costs, and burdening caregivers and medical resources. With an increase in the aging population, the prevalence of these diseases is expected to rise, increasing the economic burden. Due to the progressive nature of these neurodegenerative diseases, early detection is crucial to slow down the disease progression. While conventional medical technologies can detect cerebral blood flow variations, they are not suitable for regular monitoring due to limited accessibility, high operational costs, and the need for medical supervision. This highlights the need for portable sensors that can detect cognitive load, potentially leading to early dementia detection.

Portable Radio Frequency (RF) technologies have the potential to revolutionize diagnostics by providing non-invasive, cost-effective, portable and wearable devices. These wearable sensing and imaging devices could offer timely and accurate monitoring, enabling early intervention and better disease management. This proactive approach could improve patient outcomes and reduce the overall burden on healthcare systems. This work presents portable RF sensing for multimodal detection of cognitive load and neurodegenerative diseases. The non-invasive RF sensors are designed, developed, and evaluated on artificial brain phantoms and human subjects to validate and demonstrate their efficacy. The sensing mechanism employs AI and machine learning methods for accurate classification and real-time diagnostics.

Moreover, the RF sensors are utilized for portable brain imaging to monitor stroke and brain atrophy. This research provides an innovative approach to transforming mobile healthcare by offering portable imaging analysis, diagnosis, and prognosis with minimal medical supervision.